by Moonshot AI

MoonshotAI: Kimi K3.

multimodal open weights datacenter 2780B params 1M ctx
Cheapest input
$0.192/M
on OpenRouter
Cheapest output
$14.25/M
on DeepInfra
Smallest GPU
8× AMD MI325
$25.36/hr
Run it yourself

Cheapest hardware per quantisation.

Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.

Quantisation Cheapest GPU config Total VRAM Live $/hr tokens/sec
INT4
INT4 — 4-bit integer (~4× VRAM saving)
2048 GB $25.36/hr — Compare →
Just need an API?
Skip the GPU rental and call a hosted endpoint instead. See access providers on the Overview tab →